BibTeX record journals/corr/abs-2110-08440

• > Home > journals/corr/abs-2110-08440

@article{DBLP:journals/corr/abs-2110-08440,
  author       = {Naman Agarwal and
                  Syomantak Chaudhuri and
                  Prateek Jain and
                  Dheeraj Nagaraj and
                  Praneeth Netrapalli},
  title        = {Online Target Q-learning with Reverse Experience Replay: Efficiently
                  finding the Optimal Policy for Linear MDPs},
  journal      = {CoRR},
  volume       = {abs/2110.08440},
  year         = {2021},
  url          = {https://arxiv.org/abs/2110.08440},
  eprinttype    = {arXiv},
  eprint       = {2110.08440},
  timestamp    = {Fri, 22 Oct 2021 13:33:09 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2110-08440.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}